Balrog
Balanced reasoning and logic games evaluation benchmark.
16rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Standard error (lower is better)
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Grok 4 | 43.60 | Grok 4 x-ai-grok-4 | Imported | 2026-05-06 |
| 2 | Gemini 2.5 Pro (Jun 2025) | 43.30 |  Gemini 2.5 Pro google-gemini-2.5-pro | Imported | 2026-05-06 |
| 3 | DeepSeek R1 | 34.90 |  R1 deepseek-r1 | Imported | 2026-05-06 |
| 4 | GPT-5.2 | 32.80 |  GPT-5.2 openai-gpt-5.2 | Imported | 2026-05-06 |
| 5 | Claude 3.7 Sonnet | 32.60 |  Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-05-06 |
| 6 | GPT-4o | 32.30 | GPT-4o openai-gpt-4o | Imported | 2026-05-06 |
| 7 | Grok-3 mini | 29.50 | Grok 3 Mini x-ai-grok-3-mini | Imported | 2026-05-06 |
| 8 | Llama 3.1 405B | 27.90 | — | Imported | 2026-05-06 |
| 9 | Llama 3.3 70B | 23 |  Llama 3.3 70B Instruct meta-llama-llama-3.3-70b-instruct | Imported | 2026-05-06 |
| 10 | Gemini 1.5 Flash | 21 | — | Imported | 2026-05-06 |
| 11 | DeepSeek V3 | 19.50 | DeepSeek V3 deepseek-deepseek-chat | Imported | 2026-05-06 |
| 12 | Claude 3.5 Haiku | 19.30 | Claude 3.5 Haiku anthropic-claude-3.5-haiku | Imported | 2026-05-06 |
| 13 | Mistral Large | 17.60 |  Mistral Large mistralai-mistral-large | Imported | 2026-05-06 |
| 14 | gpt-4o-mini-2024-07-18 | 17.40 | GPT-4o-mini (2024-07-18) openai-gpt-4o-mini-2024-07-18 | Imported | 2026-05-06 |
| 15 | Qwen2.5-Max | 16.20 | — | Imported | 2026-05-06 |
| 16 | Phi-4 | 11.60 |  Phi 4 microsoft-phi-4 | Imported | 2026-05-06 |
No matching rows.